command-center/agent/memories/--home-blank-Projects-serverAppConfig--/rollout_summaries/01a0f190-490b-765e-b62d-21e28c3c0ec0-ds41_flash_research.md at 942787f0f2eb3b9697524159e894405039e6f4f8

Files

T

Frank 5b08896e4e chore(memory): snapshot auto-learned memory and renamed workstation skills

--home-blank-.omp--: MEMORY.md +140 / learned.md / memory_summary.md /
raw_memories.md +1002 rewritten by auto-learn after the model rename,
frank-medium split-balance and bottleneck studies. Skills renamed to
single-topic buckets: dotfile-git-workflow -> ghostty-text-aa +
niri-display-rotation + noctalia-theme, handy-service-mgmt ->
handy-flm-inference, inference-runtime -> llama-cpp-parallelism.

--home-blank-Projects-serverAppConfig--: 38 new rollout summaries,
raw_memories.md/MEMORY.md refreshed, skills re-bucketed (bench-protocol,
llm-fleet-model-swap, rootless-quadlet-log-retrieval, orchestration-quadlet).

Per-worktree bucket (wt-20261006-122204) is now gitignored, not committed.

2026-10-09 13:17:53 -07:00

441 B

Raw Blame History

thread_id: 01a0f190-490b-765e-b62d-21e28c3c0ec0 updated_at: 1790760416

Deep research on DeepSeek 4.1 Flash quantizations for the current hardware (2x R9700 gfx1201 + 246 GiB DDR5 RAM). Identified vcruz305 Q2_K as the optimal fit for the backbone (~191 GiB) and GSQ-RCO 3.0-bit as the high-quality alternative. Key bottleneck is RAM bandwidth (42 GB/s), limiting decode to ~6-11 tok/s. Next step: Build native HIP version from the fork.

441 B Raw Blame History

441 B

Raw Blame History